Accurate Retrieval of Corporate Reputation from Online Media Using Machine Learning

Abstract

Corporate reputation is an economic asset and its accurate measurement is of increasing interest in practice and science. This measurement task is difficult because reputation depends on numerous factors and stakeholders. Traditional measurement approaches have focused on human ratings and surveys, which are costly, can be conducted only infrequently and emphasize financial aspects of a corporation. Nowadays, online media with comments related to products, services, and corporations provides an abundant source for measuring reputation more comprehensively. Against this backdrop, we propose an information retrieval approach to automatically collect reputation-related text content from online media and analyze this content by machine learning-based sentiment analysis. We contribute an ontology for identifying corporations and a unique dataset of online media texts labelled by corporations' reputation. Our approach achieves an overall accuracy of 84.4%. Our results help corporations to quickly identify their reputation from online media at low cost.

Role of Text Mining to Enhance the Quality of Product Using an Unsupervised Machine Learning Approach

“…Textual data is the most available form of information on digital platform. Web data varies as compared to other sources that make it more valuable (7). In reality, internet data is broadly available to the general public, is inexpensive to acquire, and may be large in terms of controlling to this data.…”

An extensive analysis of online restaurant reviews: a case study of the Amazonian Culinary Tourism

“…In the last years, with the data volume available on the internet and diversity growth, many challenges regarding data collection and analysis in this sector have emerged [7], [8]. One of these is to analyze the immense volume of textual data, a task practically impossible to be performed manually [9]. To tackle this obstacle, computational techniques such as Text Mining can be employed in order to identify patterns and 1 Data from Brazil's Ministry of Tourism generate insights that can support the decision making process [10], [11], [6].…”